Java:转换汉字为unicode形式的字符串和转换unicode形式字符串转换成汉字
2013-11-07 16:52
302 查看
/**
*
*/
package com.sech.zengzhi.comm;
/**
* <p>Title: GU ZengZhi</p>
*
* <p>Description: GU</p>
*
* <p>Copyright: Copyright (c) 2009</p>
*
* <p>Company: GU</p>
*
* <p>CreateTime:2013-11-7 下午4:18:32</p>
*
* @author Aaron
*
* @version 1.0
*/
public class UnicodeConverter {
private static final char[] hexDigit = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A',
'B', 'C', 'D', 'E', 'F' };
private static char toHex(int nibble) {
return hexDigit[(nibble & 0xF)];
}
/**
* 将字符串编码成 Unicode 形式的字符串. 如 "黄" to "\u9EC4"
* Converts unicodes to encoded \\uxxxx and escapes
* special characters with a preceding slash
*
* @param theString
* 待转换成Unicode编码的字符串。
* @param escapeSpace
* 是否忽略空格,为true时在空格后面是否加个反斜杠。
* @return 返回转换后Unicode编码的字符串。
*/
public static String toEncodedUnicode(String theString, boolean escapeSpace) {
int len = theString.length();
int bufLen = len * 2;
if (bufLen < 0) {
bufLen = Integer.MAX_VALUE;
}
StringBuffer outBuffer = new StringBuffer(bufLen);
for (int x = 0; x < len; x++) {
char aChar = theString.charAt(x);
// Handle common case first, selecting largest block that
// avoids the specials below
if ((aChar > 61) && (aChar < 127)) {
if (aChar == '\\') {
outBuffer.append('\\');
outBuffer.append('\\');
continue;
}
outBuffer.append(aChar);
continue;
}
switch (aChar) {
case ' ':
if (x == 0 || escapeSpace) outBuffer.append('\\');
outBuffer.append(' ');
break;
case '\t':
outBuffer.append('\\');
outBuffer.append('t');
break;
case '\n':
outBuffer.append('\\');
outBuffer.append('n');
break;
case '\r':
outBuffer.append('\\');
outBuffer.append('r');
break;
case '\f':
outBuffer.append('\\');
outBuffer.append('f');
break;
case '=': // Fall through
case ':': // Fall through
case '#': // Fall through
case '!':
outBuffer.append('\\');
outBuffer.append(aChar);
break;
default:
if ((aChar < 0x0020) || (aChar > 0x007e)) {
// 每个unicode有16位,每四位对应的16进制从高位保存到低位
outBuffer.append('\\');
outBuffer.append('u');
outBuffer.append(toHex((aChar >> 12) & 0xF));
outBuffer.append(toHex((aChar >> 8) & 0xF));
outBuffer.append(toHex((aChar >> 4) & 0xF));
outBuffer.append(toHex(aChar & 0xF));
} else {
outBuffer.append(aChar);
}
}
}
return outBuffer.toString();
}
/**
* 从 Unicode 形式的字符串转换成对应的编码的特殊字符串。 如 "\u9EC4" to "黄".
* Converts encoded \\uxxxx to unicode chars
* and changes special saved chars to their original forms
*
* @param in
* Unicode编码的字符数组。
* @param off
* 转换的起始偏移量。
* @param len
* 转换的字符长度。
* @param convtBuf
* 转换的缓存字符数组。
* @return 完成转换,返回编码前的特殊字符串。
*/
public static String fromEncodedUnicode(char[] in, int off, int len) {
char aChar;
char[] out = new char[len]; // 只短不长
int outLen = 0;
int end = off + len;
while (off < end) {
aChar = in[off++];
if (aChar == '\\') {
aChar = in[off++];
if (aChar == 'u') {
// Read the xxxx
int value = 0;
for (int i = 0; i < 4; i++) {
aChar = in[off++];
switch (aChar) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
value = (value << 4) + aChar - '0';
break;
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
value = (value << 4) + 10 + aChar - 'a';
break;
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
value = (value << 4) + 10 + aChar - 'A';
break;
default:
throw new IllegalArgumentException("Malformed \\uxxxx encoding.");
}
}
out[outLen++] = (char) value;
} else {
if (aChar == 't') {
aChar = '\t';
} else if (aChar == 'r') {
aChar = '\r';
} else if (aChar == 'n') {
aChar = '\n';
} else if (aChar == 'f') {
aChar = '\f';
}
out[outLen++] = aChar;
}
} else {
out[outLen++] = (char) aChar;
}
}
return new String(out, 0, outLen);
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s = "中国";
System.out.println("111111111:" + s);
s = toEncodedUnicode(s, true);
System.out.println("222222222:" + s);
s = fromEncodedUnicode(s.toCharArray(), 0, s.length());
System.out.println("33333333333333:" + s);
}
}
转自:http://www.blogjava.net/jjshcc/archive/2011/05/11/349991.html
*
*/
package com.sech.zengzhi.comm;
/**
* <p>Title: GU ZengZhi</p>
*
* <p>Description: GU</p>
*
* <p>Copyright: Copyright (c) 2009</p>
*
* <p>Company: GU</p>
*
* <p>CreateTime:2013-11-7 下午4:18:32</p>
*
* @author Aaron
*
* @version 1.0
*/
public class UnicodeConverter {
private static final char[] hexDigit = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A',
'B', 'C', 'D', 'E', 'F' };
private static char toHex(int nibble) {
return hexDigit[(nibble & 0xF)];
}
/**
* 将字符串编码成 Unicode 形式的字符串. 如 "黄" to "\u9EC4"
* Converts unicodes to encoded \\uxxxx and escapes
* special characters with a preceding slash
*
* @param theString
* 待转换成Unicode编码的字符串。
* @param escapeSpace
* 是否忽略空格,为true时在空格后面是否加个反斜杠。
* @return 返回转换后Unicode编码的字符串。
*/
public static String toEncodedUnicode(String theString, boolean escapeSpace) {
int len = theString.length();
int bufLen = len * 2;
if (bufLen < 0) {
bufLen = Integer.MAX_VALUE;
}
StringBuffer outBuffer = new StringBuffer(bufLen);
for (int x = 0; x < len; x++) {
char aChar = theString.charAt(x);
// Handle common case first, selecting largest block that
// avoids the specials below
if ((aChar > 61) && (aChar < 127)) {
if (aChar == '\\') {
outBuffer.append('\\');
outBuffer.append('\\');
continue;
}
outBuffer.append(aChar);
continue;
}
switch (aChar) {
case ' ':
if (x == 0 || escapeSpace) outBuffer.append('\\');
outBuffer.append(' ');
break;
case '\t':
outBuffer.append('\\');
outBuffer.append('t');
break;
case '\n':
outBuffer.append('\\');
outBuffer.append('n');
break;
case '\r':
outBuffer.append('\\');
outBuffer.append('r');
break;
case '\f':
outBuffer.append('\\');
outBuffer.append('f');
break;
case '=': // Fall through
case ':': // Fall through
case '#': // Fall through
case '!':
outBuffer.append('\\');
outBuffer.append(aChar);
break;
default:
if ((aChar < 0x0020) || (aChar > 0x007e)) {
// 每个unicode有16位,每四位对应的16进制从高位保存到低位
outBuffer.append('\\');
outBuffer.append('u');
outBuffer.append(toHex((aChar >> 12) & 0xF));
outBuffer.append(toHex((aChar >> 8) & 0xF));
outBuffer.append(toHex((aChar >> 4) & 0xF));
outBuffer.append(toHex(aChar & 0xF));
} else {
outBuffer.append(aChar);
}
}
}
return outBuffer.toString();
}
/**
* 从 Unicode 形式的字符串转换成对应的编码的特殊字符串。 如 "\u9EC4" to "黄".
* Converts encoded \\uxxxx to unicode chars
* and changes special saved chars to their original forms
*
* @param in
* Unicode编码的字符数组。
* @param off
* 转换的起始偏移量。
* @param len
* 转换的字符长度。
* @param convtBuf
* 转换的缓存字符数组。
* @return 完成转换,返回编码前的特殊字符串。
*/
public static String fromEncodedUnicode(char[] in, int off, int len) {
char aChar;
char[] out = new char[len]; // 只短不长
int outLen = 0;
int end = off + len;
while (off < end) {
aChar = in[off++];
if (aChar == '\\') {
aChar = in[off++];
if (aChar == 'u') {
// Read the xxxx
int value = 0;
for (int i = 0; i < 4; i++) {
aChar = in[off++];
switch (aChar) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
value = (value << 4) + aChar - '0';
break;
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
value = (value << 4) + 10 + aChar - 'a';
break;
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
value = (value << 4) + 10 + aChar - 'A';
break;
default:
throw new IllegalArgumentException("Malformed \\uxxxx encoding.");
}
}
out[outLen++] = (char) value;
} else {
if (aChar == 't') {
aChar = '\t';
} else if (aChar == 'r') {
aChar = '\r';
} else if (aChar == 'n') {
aChar = '\n';
} else if (aChar == 'f') {
aChar = '\f';
}
out[outLen++] = aChar;
}
} else {
out[outLen++] = (char) aChar;
}
}
return new String(out, 0, outLen);
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s = "中国";
System.out.println("111111111:" + s);
s = toEncodedUnicode(s, true);
System.out.println("222222222:" + s);
s = fromEncodedUnicode(s.toCharArray(), 0, s.length());
System.out.println("33333333333333:" + s);
}
}
转自:http://www.blogjava.net/jjshcc/archive/2011/05/11/349991.html
相关文章推荐
- Java:把汉字为unicode形式的字符串和把unicode字符串转换成汉字
- 转换汉字为unicode形式的字符串和转换unicode形式字符串转换成汉字__http://www.cppblog.com/biao/archive/2010/12/21/137087.html
- 转换汉字为unicode形式的字符串和转换unicode形式字符串转换成汉字
- 【小工具类】Unicode字符串转换成汉字
- Java将数字字符串转换成中文形式
- Android Java中将unicode的汉字码转换成utf-8格式的汉字
- JAVA方法 字符串与unicode的相互转换
- Java 汉字转换为拼音字符串
- 以Base64字符串形式上传文件——服务器端Java/Servlet接受请求数据中的字符串内容并转换成文件
- java之配置文件中的汉字和unicode相互转换
- java实用方法系列 list转换为字符串的形式
- 把unicode编码的十六进制字符串转换为汉字(Python2.7)
- java 汉字转换成unicode
- java自动处理unicode形式的字符串
- java角度字符串表示形式和double形式的转换
- 将Fri May 04 17:25:34 CST 2012形式的日期字符串转换成java.util.Date对象的方法
- URL参数中汉字转换为16进制Unicode形式
- JAVA方法 字符串与unicode的相互转换
- java的类型转换(常用字符串,日期,汉字符号等!!)
- 汉字转换成Unicode,简单的java实现方法